© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27351
    Prev
    Next
    INDEX
    Explanations

    HTML script tags and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Æ°ng
    -0.07
    .da
    -0.07
     Kop
    -0.06
    scal
    -0.06
    inyin
    -0.06
    ses
    -0.06
     Quang
    -0.06
    ÑıÑĩи
    -0.06
    kop
    -0.06
    enance
    -0.06
    POSITIVE LOGITS
    osi
    0.07
    ed
    0.07
    cona
    0.07
     conc
    0.07
    assi
    0.07
    olle
    0.07
    oro
    0.07
     Conc
    0.06
     veniam
    0.06
    lla
    0.06
    Activations Density 0.006%

    No Known Activations